TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912520670806016 |
|---|---|
| author | Tang, Yuchi Esnaola, Iñaki Panoutsos, George |
| author_facet | Tang, Yuchi Esnaola, Iñaki Panoutsos, George |
| contents | Existing post-hoc model-agnostic methods generate external explanations for opaque models, primarily by locally attributing the model output to its input features. However, they often lack an explicit and systematic framework for quantifying the contribution of individual features. Building on the Taylor expansion framework introduced by Deng et al. (2024) to unify existing local attribution methods, we propose a rigorous set of postulates -- "precision", "federation", and "zero-discrepancy" -- to govern Taylor term-specific attribution. Guided by these postulates, we introduce TaylorPODA (Taylor expansion-derived imPortance-Order aDapted Attribution), which incorporates an additional "adaptation" property. This property enables alignment with task-specific goals, especially in post-hoc settings lacking ground-truth explanations. Empirical evaluations demonstrate that TaylorPODA achieves competitive results against baseline methods, providing principled and visualization-friendly explanations. This work enhances the trustworthy deployment of opaque models by offering explanations with stronger theoretical grounding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models Tang, Yuchi Esnaola, Iñaki Panoutsos, George Machine Learning Artificial Intelligence Existing post-hoc model-agnostic methods generate external explanations for opaque models, primarily by locally attributing the model output to its input features. However, they often lack an explicit and systematic framework for quantifying the contribution of individual features. Building on the Taylor expansion framework introduced by Deng et al. (2024) to unify existing local attribution methods, we propose a rigorous set of postulates -- "precision", "federation", and "zero-discrepancy" -- to govern Taylor term-specific attribution. Guided by these postulates, we introduce TaylorPODA (Taylor expansion-derived imPortance-Order aDapted Attribution), which incorporates an additional "adaptation" property. This property enables alignment with task-specific goals, especially in post-hoc settings lacking ground-truth explanations. Empirical evaluations demonstrate that TaylorPODA achieves competitive results against baseline methods, providing principled and visualization-friendly explanations. This work enhances the trustworthy deployment of opaque models by offering explanations with stronger theoretical grounding. |
| title | TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.10643 |